Merge branch 'netdev_page_frags'

Alexander Duyck says:

====================
Refactor netdev page frags and move them into mm/

This patch series addresses several things.

First I found an issue in the performance of the pfmemalloc check from
build_skb.  To work around it I have provided a cached copy of pfmemalloc
to be used in __netdev_alloc_skb and __napi_alloc_skb.

Second I moved the page fragment allocation logic into the mm tree and
added functionality for freeing page fragments.  I had to fix igb before I
could do this as it was using a reference to NETDEV_FRAG_PAGE_MAX_SIZE
incorrectly.

Finally I went through and replaced all of the duplicate code that was
calling put_page and replaced it with calls to skb_free_frag.

With these changes in place a simple receive and drop test increased from a
packet rate of 8.9Mpps to 9.8Mpps.  The gains breakdown as follows:

8.9Mpps	Before			9.8Mpps	After
------------------------	------------------------
7.8%	put_compound_page	9.1%	__free_page_frag
3.9%	skb_free_head
1.1%	put_page

4.9%	build_skb		3.8%	__napi_alloc_skb
2.5%	__alloc_rx_skb
1.9%	__napi_alloc_skb
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 7 insertions, 12 deletions

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 983eb4e6f7aa..74dc15055971 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -2079,11 +2079,6 @@ static void *e1000_alloc_frag(const struct e1000_adapter *a)
 	return data;
 }
 
-static void e1000_free_frag(const void *data)
-{
-	put_page(virt_to_head_page(data));
-}
-
 /**
  * e1000_clean_rx_ring - Free Rx Buffers per Queue
  * @adapter: board private structure
@@ -2107,7 +2102,7 @@ static void e1000_clean_rx_ring(struct e1000_adapter *adapter,
 						 adapter->rx_buffer_len,
 						 DMA_FROM_DEVICE);
 			if (buffer_info->rxbuf.data) {
-				e1000_free_frag(buffer_info->rxbuf.data);
+				skb_free_frag(buffer_info->rxbuf.data);
 				buffer_info->rxbuf.data = NULL;
 			}
 		} else if (adapter->clean_rx == e1000_clean_jumbo_rx_irq) {
@@ -4594,28 +4589,28 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 			data = e1000_alloc_frag(adapter);
 			/* Failed allocation, critical failure */
 			if (!data) {
-				e1000_free_frag(olddata);
+				skb_free_frag(olddata);
 				adapter->alloc_rx_buff_failed++;
 				break;
 			}
 
 			if (!e1000_check_64k_bound(adapter, data, bufsz)) {
 				/* give up */
-				e1000_free_frag(data);
-				e1000_free_frag(olddata);
+				skb_free_frag(data);
+				skb_free_frag(olddata);
 				adapter->alloc_rx_buff_failed++;
 				break;
 			}
 
 			/* Use new allocation */
-			e1000_free_frag(olddata);
+			skb_free_frag(olddata);
 		}
 		buffer_info->dma = dma_map_single(&pdev->dev,
 						  data,
 						  adapter->rx_buffer_len,
 						  DMA_FROM_DEVICE);
 		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
-			e1000_free_frag(data);
+			skb_free_frag(data);
 			buffer_info->dma = 0;
 			adapter->alloc_rx_buff_failed++;
 			break;
@@ -4637,7 +4632,7 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 					 adapter->rx_buffer_len,
 					 DMA_FROM_DEVICE);
 
-			e1000_free_frag(data);
+			skb_free_frag(data);
 			buffer_info->rxbuf.data = NULL;
 			buffer_info->dma = 0;